Calipsocean meeting
05/03/2024
Role of plankton in C cycle
C export mostly estimated through modeling
Limited representation of zooplankton diversity
Can we use observations and machine learning to improve the representation of zooplankton diversity in ESM?
*plankton = zooplankton **Here, we will use POC 1000 m as a proxy for carbon export.
As in Wang et al., 2023.
Yearly climatologies from GLODAPv2.
temperature
silicate
phosphate
oxygen
NPP
alkalinity
DIC
DOC
UVP5 dataset: 2876 profiles
Functional diversity metrics (Magneville et al. 2022)
→ morphological diversity metrics (Beck et al., 2023)
morphological richness
morphological divergence
morphological evenness
…
by taxa-region matches?
Benedetti et al., 2023 (copepods only)
Placeholder
Placeholder
439 data points
Training* VS test set, stratified by POC.
TODOs
Account for spatial autocorrelation (spatial CV)
Get more robust estimates of R² (nested CV)
Response variable:
uni- or multivariate
~normally distributed → log(POC)
Flexibility for predictors, handles interactions.
Complex & non-linear relationships.
Easy interpretation & implementation.
POC ~ temperature + silicate + phosphate + oxygen + NPP + alkalinity + DIC
R² = 91.0%
Good prediction!
POC ~ all plankton metrics
R² = 57.1%
OK prediction!
Best predictors:
ta. richness ×2
mo. richness
POC ~ ta_ric_3 + ta_mast + mo_ric
R² = 38.8%
OK prediction!
POC ~ ta_ric_3 + ta_mast + mo_ric
POC response to plankton descriptors.
TODO: Merge both descriptors of taxonomic richness into one.
ta_ric_3 + ta_mast + mo_ric ~ temperature + silicate + phosphate + oxygen + NPP + alkalinity + DIC
Mult. R² = 37.8%
OK prediction!